Deep Learning for Search and Matching Models

64 Pages Posted: 15 Apr 2024 Last revised: 4 Feb 2025

See all articles by Jonathan Payne

Jonathan Payne

Princeton University

Adam Rebei

Stanford University

Yucheng Yang

University of Zurich; Swiss Finance Institute

Date Written: February 15, 2024

Abstract

We develop a new method to globally solve and estimate search and matching models with aggregate shocks and heterogeneous agents. We characterize general equilibrium as a high-dimensional partial differential equation with the distribution as a state variable. We then use deep learning to solve the model and estimate economic parameters using the simulated method of moments. This allows us to study a wide class of search markets where the distribution affects agent decisions and compute variables (e.g. wages and prices) that were previously unattainable. In applications to labor search models, we show that distribution feedback plays an important role in amplification and that positive assortative matching weakens in prolonged expansions, disproportionately benefiting low-wage workers.

Keywords: Search and Matching, Distribution Feedback, Two-sided Heterogeneity, Business Cycles, Sorting, Over-the-Counter Financial Markets, Deep learning, Financial Markets

Suggested Citation

Payne, Jonathan and Rebei, Adam and Yang, Yucheng, Deep Learning for Search and Matching Models (February 15, 2024). Swiss Finance Institute Research Paper No. 25-05, Available at SSRN: https://ssrn.com/abstract=4768566 or http://dx.doi.org/10.2139/ssrn.4768566

Jonathan Payne

Princeton University ( email )

Adam Rebei

Stanford University ( email )

Yucheng Yang (Contact Author)

University of Zurich ( email )

Rämistrasse 71
Zürich, CH-8006
Switzerland

Swiss Finance Institute ( email )

c/o University of Geneva
40, Bd du Pont-d'Arve
CH-1211 Geneva 4
Switzerland

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
340
Abstract Views
1,019
Rank
182,745
PlumX Metrics